Tensorflow Keras RMSE 指标 returns 与我自己构建的 RMSE 损失函数不同的结果

Question

这是一个回归问题

我的自定义 RMSE 损失：

def root_mean_squared_error_loss(y_true, y_pred):
    return tf.keras.backend.sqrt(tf.keras.losses.MSE(y_true, y_pred))

训练代码示例，其中 create_model returns 一个密集的全连接序列模型

from tensorflow.keras.metrics import RootMeanSquaredError
model = create_model()
model.compile(loss=root_mean_squared_error_loss, optimizer='adam', metrics=[RootMeanSquaredError()])

model.fit(train_.values,
          targets,
          validation_split=0.1,
          verbose=1,
          batch_size=32)

Train on 3478 samples, validate on 387 samples
Epoch 1/100
3478/3478 [==============================] - 2s 544us/sample - loss: 1.1983 - root_mean_squared_error: 0.7294 - val_loss: 0.7372 - val_root_mean_squared_error: 0.1274
Epoch 2/100
3478/3478 [==============================] - 1s 199us/sample - loss: 0.8371 - root_mean_squared_error: 0.3337 - val_loss: 0.7090 - val_root_mean_squared_error: 0.1288
Epoch 3/100
3478/3478 [==============================] - 1s 187us/sample - loss: 0.7336 - root_mean_squared_error: 0.2468 - val_loss: 0.6366 - val_root_mean_squared_error: 0.1062
Epoch 4/100
3478/3478 [==============================] - 1s 187us/sample - loss: 0.6668 - root_mean_squared_error: 0.2177 - val_loss: 0.5823 - val_root_mean_squared_error: 0.0818

我预计损失和 root_mean_squared_error 具有相同的值，为什么会有差异？

Answer 1

两个主要区别，来自 source code：

RMSE 是一个 有状态的 指标（它保持记忆） - 你的是无状态的
应用平方根after taking a global mean, not before an axis=-1 mean like MSE does
- 由于 1，2 涉及更多：取运行个数量的平均值 total，相对于另一个运行个数量 count;两个数量都通过 RMSE.reset_states().

原始公式修复很容易 - 但集成有状态性需要工作，这超出了这个问题的范围；参考源码看how it's done。 2 的修复与比较，如下。

import numpy as np
import tensorflow as tf
from tensorflow.keras.metrics import RootMeanSquaredError as RMSE

def root_mean_squared_error_loss(y_true, y_pred):
    return tf.sqrt(tf.reduce_mean(tf.math.squared_difference(y_true, y_pred)))

np.random.seed(0)

#%%###########################################################################
rmse = RMSE(dtype='float64')
rmsel = root_mean_squared_error_loss

x1 = np.random.randn(32, 10)
y1 = np.random.randn(32, 10)
x2 = np.random.randn(32, 10)
y2 = np.random.randn(32, 10)

#%%###########################################################################
print("TensorFlow RMSE:")
print(rmse(x1, y1))
print(rmse(x2, y2))
print("=" * 46)
print(rmse(x1, y1))
print(rmse(x2, y2))

print("\nMy RMSE:")
print(rmsel(x1, y1))
print(rmsel(x2, y2))

TensorFlow RMSE:
tf.Tensor(1.4132492562096124, shape=(), dtype=float64)
tf.Tensor(1.3875944990740972, shape=(), dtype=float64)
==============================================
tf.Tensor(1.3961984634354354, shape=(), dtype=float64)  # same inputs, different result
tf.Tensor(1.3875944990740972, shape=(), dtype=float64)  # same inputs, different result

My RMSE:
tf.Tensor(1.4132492562096124, shape=(), dtype=float64)  # first result agrees
tf.Tensor(1.3614563994283353, shape=(), dtype=float64)  # second differs since stateless

Tensorflow Keras RMSE 指标 returns 与我自己构建的 RMSE 损失函数不同的结果

Tensorflow Keras RMSE metric returns different results than my own built RMSE loss function

python

keras

tensorflow

loss-function

tf.keras